检索结果-内蒙古大学图书馆

Cortical transcriptome analysis after spinal cord injury reveals the regenerative mechanism of central nervous system in CRMP2 knock-in mice

引用

Neural Regeneration Research 2021年第7期16卷 1258-1265页

作者： Ayaka Sugeno Wenhui Piao Miki Yamazaki Kiyofumi Takahashi Koji Arikawa Hiroko Matsunaga Masahito Hosokawa Daisuke Tominaga Yoshio Goshima Haruko Takeyama Toshio Ohshima Laboratory for Molecular Brain Science Department of Life Science and Medical BioscienceGraduate School of Advanced Science and EngineeringWaseda UniversityTokyoJapan Biomolecular Engineering Laboratory Department of Life Science and Medical BioscienceGraduate School of Advanced Science and EngineeringWaseda UniversityTokyoJapan Computational Bio Big-Data Open Innovation Laboratory(CBBD-OIL) National Institute of Advanced Industrial Science and Technology(AIST)TokyoJapan Research Organization for Nano and Life Innovation Waseda UniversityTokyoJapan Institute for Advanced Research of Biosystem Dynamics Waseda Research Institute for Science and EngineeringGraduate School of Advanced Science and EngineeringWaseda UniversityTokyoJapan Cellular and Molecular Biotechnology Research Institute National Institute of Advanced Industrial Science and Technology(AIST)TsukubaJapan Department of Molecular Pharmacology and Neurobiology Graduate School of MedicineYokohama City UniversityYokohamaJapan

Recent studies have shown that mutation at Ser522 causes inhibition of collapsin response mediator protein 2(CRMP2) phosphorylation and induces axon elongation and partial recovery of the lost sensorimotor function after spinal cord injury(SCI).We aimed to reveal the intracellular mechanism in axotomized neurons in the CRMP2 knock-in(CRMP2KI) mouse model by performing transcriptome analysis in mouse sensorimotor cortex using micro-dissection punching *** to that, we analyzed the structural pathophysiology in axotomized or neighboring neurons after SCI and found that somatic atrophy and dendritic spine reduction in sensorimotor cortex were suppressed in CRMP2KI *** analysis of the transcriptome has aided in the identification of four hemoglobin genes Hba-a1, Hba-a2, Hbb-bs, and Hbb-bt that are significantly upregulated in wild-type mice with concomitant upregulation of genes involved in the oxidative phosphorylation and ribosomal pathways after ***, we observed substantial upregulation in channel activity genes and downregulation of genes regulating vesicles, synaptic function, glial cell differentiation in CRMP2KI ***, the transcriptome profile of CRMP2KI mice has been discussed wherein energy metabolism and neuronal pathways were found to be differentially *** results showed that CRMP2KI mice displayed improved SCI pathophysiology not only via microtubule stabilization in neurons, but also possibly via the whole metabolic system in the central nervous system, response changes in glial cells, and *** together, we reveal new insights on SCI pathophysiology and the regenerative mechanism of central nervous system by the inhibition of CRMP2 phosphorylation at *** these experiments were performed in accordance with the guidelines of the Institutional Animal Care and Use Committee at Waseda University, Japan(2017-A027 approved on March 21, 2017;2018-A003 approved on March 25, 2018;2019-A026 approved on March

关键词： CNS regeneration cortex CRMP2 hemoglobin metabolic pathway spinal cord injury spine transcriptome

来源：评论

学校读者我要写书评

暂无评论

Target networks and over-parameterization stabilize off-policy bootstrapping with function approximation 24

Target networks and over-parameterization stabilize off-poli...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Fengdi Che Chenjun Xiao Jincheng Mei Bo Dai Ramki Gummadi Oscar A Ramirez Christopher K Harris A. Rupam Mahmood Dale Schuurmans Department of Computing Science University of Alberta School of Data Science The Chinese University of Hong Kong Shenzhen Google DeepMind Google DeepMind and School of Computational Science and Engineering Georgia Tech Figure and Google Google and Uber Department of Computing Science University of Alberta and CIFAR AI Chair Amii Department of Computing Science University of Alberta and Google DeepMind and CIFAR AI Chair Amii

We prove that the combination of a target network and over-parameterized linear function approximation establishes a weaker convergence condition for bootstrapped value estimation in certain cases, even with off-policy data. Our condition is naturally satisfied for expected updates over the entire state-action space or learning with a batch of complete trajectories from episodic Markov decision processes. Notably, using only a target network or an over-parameterized model does not provide such a convergence guarantee. Additionally, we extend our results to learning with truncated trajectories, showing that convergence is achievable for all tasks with minor modifications, akin to value truncation for the final states in trajectories. Our primary result focuses on temporal difference estimation for prediction, providing high-probability value estimation error bounds and empirical analysis on Baird's counterexample and a Four-room task. Furthermore, we explore the control setting, demonstrating that similar convergence conditions apply to Q-learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic Optimization for Path Planning in UAV Networks for Long-Distance Inspection Tasks

Metaheuristic Optimization for Path Planning in UAV Networks...

引用

International Conference on System Modeling & Advancement in Research Trends (SMART)

作者： J. Akshya M. Manochitra R. Indu Poornima T. Jeevitha M. Saravanakumar M. Sundarrajan Mani Deepak Choudhry Department of Computational Intelligence SRM Institute of Science and Technology Chennai Computer Science and Engineering (Cyber Security) Dr. N.G.P. Institute of Technology Coimbatore Department of Information Technology KGiSL Institute of Technology Coimbatore Department of Artificial Intelligence and Data Science Nehru Institute of Engineering and Technology Coimbatore Department of Networking and Communications SRM Institute of Science and Technology Chennai Deportment of Computing Technologies SRM Institute of Science and Technology Chennai

ISBN: (数字)9798350380583

ISBN: (纸本)9798350380590

With broad applicability in surveillance, delivery, and environmental monitoring, multi-drone path planning has received a great deal of attention recently. So far, wide applicability has been explored by various applications of Genetic Algorithms, Particle Swarm Optimization, and Ant Colony Optimization, which have already established reliable solutions to navigation and coverage through drone path optimization. However, in dynamic, obstacle-dense environments, these algorithms fail to adapt in real-time with energy efficiency. Traditional GA and PSO approaches can be effective for generating an initial path but fail to respond to collision avoidance and efficient resource management. In complex and unpredictable conditions, ACO fails to converge rapidly, which leads to suboptimal paths and increased energy consumption. To overcome such barriers, we present here an HGARL for enhanced multi-drone path optimization. The proposed algorithm thus combines the population-based search capability of GA with RL's adaptive learning ability, therefore providing an algorithm that in addition to finding optimal paths adjusts the paths according to changing environmental situations. HGARL presents better performance compared to existing methods. In path convergence, it reaches up to 15%, and in energy consumption, it reduces up to 20% with safe collision-free navigation. The strong potential of HGARL for robust, efficient, and adaptive solutions of real-time multi-drone operation in complex and dynamic environments has set a new benchmark for UAV path planning.

关键词： Energy consumption Navigation Heuristic algorithms Reinforcement learning Path planning Real-time systems Reliability Genetic algorithms Drones Convergence

来源：评论

学校读者我要写书评

暂无评论

A decentralized Nesterov gradient method for stochastic optimization over unbalanced directed networks

A decentralized Nesterov gradient method for stochastic opti...

引用

作者： Hu, Jinhui Xia, Dawen Cheng, Huqiang Feng, Liping Ji, Lianghao Guo, Jing Li, Huaqing Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing China College of Data Science and Information Engineering Guizhou Minzu University Guiyang China Department of Computer Science Xinzhou Teachers University Shanxi China Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing China

Decentralized stochastic gradient methods play significant roles in large-scale optimization that finds many practical applications in machine learning and coordinated control. This paper studies optimization problems over unbalanced directed networks, where the mutual goal of agents in the network is to optimize a global objective function expressed as a sum of local objective functions. Each agent using only local computation and communication in the networks is assumed to get access to a stochastic first-order oracle. In order to devise a noise-tolerant decentralized algorithm with accelerated linear convergence, a decentralized Nesterov gradient algorithm with the constant step-size and parameter using stochastic gradients is proposed in this paper. The proposed algorithm employing a gradient-tracking technique is proved to converge linearly to an error ball around the optimal solution via the analysis on a linear system when the positive constant step-size and parameter are sufficiently small. We further recover the exact linear convergence for the proposed algorithm with exact gradients under the same selection conditions of the constant step-size and parameter. Some real-world data sets are used in simulations to validate the correctness of the theoretical findings and practicability of the proposed algorithm. © 2020 Chinese Automatic Control Society and John Wiley & Sons Australia, Ltd.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Building of Geographic Information System for Monitoring of Dams in the Republic of Kazakhstan

Building of Geographic Information System for Monitoring of ...

引用

International Conference on Information science and Communications Technologies (ICISCT)

作者： Balgaisha Mukanova Tolkyn Mirgalikyzy Kamila Tanyrbergenova Assemov Kambar Yermek Akhmetov Department of Computations and Data Science Astana IT University Astana Kazakhstan Department of Computational Science and Statistics Al Farabi Kazakh National University Almaty Kazakhstan Department of Computer Engineering Astana IT University Astana Kazakhstan RSE National Center on Complex Processing of Mineral Raw Materials of the Republic of Kazakhstan Almaty Kazakhstan

ISBN: (数字)9798331527921

ISBN: (纸本)9798331527938

We describe the structure and main components of the geographic information system devoted to collecting and monitoring dams and dikes in the Republic of Kazakhstan. We also propose the structure of the main tables of the relational database system, types of monitoring work, including drone flybys, and system functionality for different users. Methods of using available open-source data to identify unregistered dams are discussed.

关键词： Surveys Information science Dams Levee Relational databases Communications technology data mining Monitoring Geographic information systems Drones

来源：评论

学校读者我要写书评

暂无评论

Building of Geographic Information System for Monitoring of Dams in the Republic of Kazakhstan

Building of Geographic Information System for Monitoring of ...

引用

2024 International Conference on Information science and Communications Technologies, ICISCT 2024

作者： Mukanova, Balgaisha Mirgalikyzy, Tolkyn Tanyrbergenova, Kamila Kambar, Assemov Akhmetov, Yermek Astana It University Department of Computations and Data Science Astana Kazakhstan Al Farabi Kazakh National University Department of Computational Science and Statistics Almaty Kazakhstan Astana It University Department of Computer Engineering Astana Kazakhstan Rse National Center on Complex Processing of Mineral Raw Materials of the Republic of Kazakhstan Almaty Kazakhstan

ISBN: (纸本)9798331527921

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and OpenCV: A Powerful Combination for Driver Drowsiness Detection

Machine Learning and OpenCV: A Powerful Combination for Driv...

引用

International Conference on Communication, Computing and Internet of Things (IC3IoT)

作者： A Siva Kumar Pv Gopirajan Jayaraj Ramasamy Beulah Jackson Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur Chennai India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur Campus Chennai India Department of IT Faculty of Engineering and Technology Botho University Botswana-Africa Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Chennai India

ISBN: (数字)9798350352689

ISBN: (纸本)9798350352696

Driver fatigue is a significant contributor to road accidents worldwide, and there is a need for efficient driver drowsiness detection systems to prevent such accidents. Computer vision techniques like OpenCV have recently been utilized to develop such strategies. This proposed work investigates the use of machine learning models and OpenCV Python package for driver drowsiness detection. The proposed system uses a camera to continuously capture the driver’s face and applies image processing techniques to identify drowsiness. The system detects blinks by monitoring the driver’s eyes and measuring the frequency and duration of eyelid closures. The real-time experiments conducted with the proposed method showed high accuracy in detecting drowsiness, and the system can be implemented in various settings, including cars and heavy vehicles. Ultimately, the system has some potential to reduce accidents caused by driver fatigue, thereby enhancing road safety.

关键词： Support vector machines Face recognition Machine learning Feature extraction Fatigue Real-time systems Vectors

来源：评论

学校读者我要写书评

暂无评论

COMPARING FORWARD AND INVERSE DESIGN PARADIGMS: A CASE STUDY ON REFRACTORY HIGH-ENTROPY ALLOYS

arXiv

引用

arXiv 2023年

作者： Debnath, Arindam Li, Wenjie Ahn, Marcia Shang, Shunli Liu, Zi-Kui Raman, Lavanya Krajewski, Adam M. Lin, Shuang Beese, Allison M. Reinhart, Wesley F. Department of Materials Science and Engineering Pennsylvania State University University ParkPA16802 United States Department of Materials Science and Engineering Department of Mechanical Engineering Pennsylvania State University University ParkPA16802 United States Department of Materials Science and Engineering Institute for Computational and Data Sciences Pennsylvania State University University ParkPA16802 United States

The rapid design of advanced materials is a topic of great scientific interest. The conventional, "forward" paradigm of materials design involves evaluating multiple candidates to determine the best candidate that matches the target properties. However, recent advances in the field of deep learning have given rise to the possibility of an "inverse" design paradigm for advanced materials, wherein a model provided with the target properties is able to find the best candidate. Being a relatively new concept, there remains a need to systematically evaluate how these two paradigms perform in practical applications. Therefore, the objective of this study is to directly, quantitatively compare the forward and inverse design modeling paradigms. We do so by considering two case studies of refractory high-entropy alloy design with different objectives and constraints and comparing the inverse design method to other forward schemes like localized forward search, high throughput screening, and multi objective optimization. Copyright © 2023, The Authors. All rights reserved.

关键词： Refractory materials

来源：评论

学校读者我要写书评

暂无评论

Deep Single Shot Musical Instrument Identification using Scalograms

Deep Single Shot Musical Instrument Identification using Sca...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Debdutta Chatterjee Arindam Dutta Dibakar Sil Aniruddha Chandra Department of Electronics and communication Engineering National Institute Of Technology Durgapur India Department of Computational and Data Sciences Indian Institute of Science Bangalore India Steradian Semiconductors Pvt. Ltd. Bangalore India

Musical instrument identification has for long had a reputation of being one of the most ill-posed problems in the field of musical information retrieval. Despite several robust attempts made at solving the problem, a timeline spanning over the last five odd decades, the problem remains an open conundrum. In this work, we take on a further complex version of the traditional problem, we attempt to solve the problem with minimal data available - one audio excerpt per class. We propose to use a convolutional Siamese network and a residual variant of the same to identify musical instruments based on the corresponding scalograms of their audio excerpts. Results obtained for two publicly available datasets validate our algorithm, achieving over 80% accuracy with only 5 sets of training data. Moreover, our proposed architectures work for both spectrograms as well as scalograms, and exhibit improvements, albeit marginal (≃ 3%), for the later input class.

关键词： Instruments Music Training data Aerospace electronics Information retrieval Artificial intelligence Spectrogram

来源：评论

学校读者我要写书评

暂无评论

Modeling of Measurement Error in Financial Returns data

arXiv

引用

arXiv 2024年

作者： Jasra, Ajay Maama, Mohamed Mijatović, Aleksandar School of Data Science The Chinese University of Hong Kong Shenzhen China Applied Mathematics and Computational Science Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia Department of Statistics University of Warwick United Kingdom

In this paper we consider the modeling of measurement error for fund returns data. In particular, given access to a time-series of discretely observed log-returns and the associated maximum over the observation period, we develop a stochastic model which models the true log-returns and maximum via a Lévy process and the data as a measurement error there-of. The main technical difficulty of trying to infer this model, for instance Bayesian parameter estimation, is that the joint transition density of the return and maximum is seldom known, nor can it be simulated exactly. Based upon the novel stick breaking representation of [12] we provide an approximation of the model. We develop a Markov chain Monte Carlo (MCMC) algorithm to sample from the Bayesian posterior of the approximated posterior and then extend this to a multilevel MCMC method which can reduce the computational cost to approximate posterior expectations, relative to ordinary MCMC. We implement our methodology on several applications including for real data. Copyright © 2024, The Authors. All rights reserved.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：